G
YouTube TikTok Games
Skip to content
View NavidBroumandfar's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report NavidBroumandfar

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
NavidBroumandfar/README.md

Navid Broumandfar

Applied AI product builder. Founder of limou and Senthira.

I came to AI through enterprise operations and data systems. Now I build products around the work people need to get done.

Building

  • limou: a personal creative AI agent for businesses.
  • Senthira: behavioral evaluation for AI agents, starting with finance.

I start with the workflow, then test what the AI actually does.

Website · LinkedIn · Email

Pinned Loading

  1. agent-terrarium agent-terrarium Public

    Bounded, auditable agent operations: agents work inside a sealed, observable terrarium — nothing leaves except through a typed-phrase human gate. Fail-closed model routing, hash-only receipts, 95 t…

    Python 1

  2. evidence-loop-visibility-engine evidence-loop-visibility-engine Public

    Evidence-first SEO, AEO, GEO and LLMO proposals through bounded Loop Engineering.

    Python 2

  3. bedrock-caseops-control-tower bedrock-caseops-control-tower Public

    Grounded AWS Bedrock document review proof with retrieval, validation, citations, structured outputs, and escalation boundaries.

    Python 1

  4. databricks-caseops-lakehouse databricks-caseops-lakehouse Public

    Databricks-native governed document preparation pipeline for provenance, extraction, validation, evaluation, and AI-ready handoff records.

    Python 1

  5. arcade-rl-studio arcade-rl-studio Public

    Local-first control plane for reproducible reinforcement-learning experiments

    Python 1

  6. agent-behavior-evals-lab agent-behavior-evals-lab Public

    Deterministic checks for saved AI agent responses and recorded tool events.

    Python